MGR: Multi-generator Based Rationalization

Wei Liu, Haozhao Wang, Jun Wang, Ruixuan Li, Xinyang Li, YuanKai Zhang, Yang Qiu


Abstract
Rationalization is to employ a generator and a predictor to construct a self-explaining NLP model in which the generator selects a subset of human-intelligible pieces of the input text to the following predictor. However, rationalization suffers from two key challenges, i.e., spurious correlation and degeneration, where the predictor overfits the spurious or meaningless pieces solely selected by the not-yet well-trained generator and in turn deteriorates the generator. Although many studies have been proposed to address the two challenges, they are usually designed separately and do not take both of them into account. In this paper, we propose a simple yet effective method named MGR to simultaneously solve the two problems. The key idea of MGR is to employ multiple generators such that the occurrence stability of real pieces is improved and more meaningful pieces are delivered to the predictor. Empirically, we show that MGR improves the F1 score by up to 20.9% as compared to state-of-the-art methods.
Anthology ID:
2023.acl-long.715
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
12771–12787
Language:
URL:
https://aclanthology.org/2023.acl-long.715
DOI:
10.18653/v1/2023.acl-long.715
Bibkey:
Cite (ACL):
Wei Liu, Haozhao Wang, Jun Wang, Ruixuan Li, Xinyang Li, YuanKai Zhang, and Yang Qiu. 2023. MGR: Multi-generator Based Rationalization. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 12771–12787, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
MGR: Multi-generator Based Rationalization (Liu et al., ACL 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/improve-issue-templates/2023.acl-long.715.pdf
Video:
 https://preview.aclanthology.org/improve-issue-templates/2023.acl-long.715.mp4